Readme
Test ANY diffuser model on Huggingface.com
How it works
- Copy the model you want to test. Example: SG161222/RealVisXL_V4.0
- Fill the form
- Run the inference
alexgenovese / test-endpoint
Use Huggingface model name to test a ANY XL model
- Public
- 10.8K runs
-
A100 (80GB)
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=alexgenovese/test-endpoint
or set up a project from scratch
Install Replicate’s Node.js client library:
npm install replicateSet the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:
import Replicate from "replicate";
import fs from "node:fs";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});Run alexgenovese/test-endpoint using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"alexgenovese/test-endpoint:7b1b908e2e28ee517404087adadabe32602530d4f44d20cfac8941b9a05ce267",
{
input: {
width: 1024,
height: 1024,
prompt: "A realistic fashion photography of an elegant 30 years old blonde woman in an hotel with one red bag. ((full shot)) 8k uhd, dslr, soft lighting, high quality, Fujifilm XT3. detailed face and detailed skin. cinematic lighting, movie still",
scheduler: "K_EULER",
base_model: "SG161222/RealVisXL_V1.0",
num_outputs: 1,
guidance_scale: 7.5,
apply_watermark: true,
negative_prompt: "worst quality, normal quality, low quality, low res, blurry, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting",
num_inference_steps: 50
}
}
);
// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"
// To write the file to disk:
fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:
pip install replicateSet the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:
import replicateRun alexgenovese/test-endpoint using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"alexgenovese/test-endpoint:7b1b908e2e28ee517404087adadabe32602530d4f44d20cfac8941b9a05ce267",
input={
"width": 1024,
"height": 1024,
"prompt": "A realistic fashion photography of an elegant 30 years old blonde woman in an hotel with one red bag. ((full shot)) 8k uhd, dslr, soft lighting, high quality, Fujifilm XT3. detailed face and detailed skin. cinematic lighting, movie still",
"scheduler": "K_EULER",
"base_model": "SG161222/RealVisXL_V1.0",
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": True,
"negative_prompt": "worst quality, normal quality, low quality, low res, blurry, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting",
"num_inference_steps": 50
}
)
print(output)To learn more, take a look at the guide on getting started with Python.
Set the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run alexgenovese/test-endpoint using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \
-H "Authorization: Bearer $REPLICATE_API_TOKEN" \
-H "Content-Type: application/json" \
-H "Prefer: wait" \
-d $'{
"version": "alexgenovese/test-endpoint:7b1b908e2e28ee517404087adadabe32602530d4f44d20cfac8941b9a05ce267",
"input": {
"width": 1024,
"height": 1024,
"prompt": "A realistic fashion photography of an elegant 30 years old blonde woman in an hotel with one red bag. ((full shot)) 8k uhd, dslr, soft lighting, high quality, Fujifilm XT3. detailed face and detailed skin. cinematic lighting, movie still",
"scheduler": "K_EULER",
"base_model": "SG161222/RealVisXL_V1.0",
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": true,
"negative_prompt": "worst quality, normal quality, low quality, low res, blurry, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting",
"num_inference_steps": 50
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:
brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/alexgenovese/test-endpoint@sha256:7b1b908e2e28ee517404087adadabe32602530d4f44d20cfac8941b9a05ce267 \
-i 'width=1024' \
-i 'height=1024' \
-i 'prompt="A realistic fashion photography of an elegant 30 years old blonde woman in an hotel with one red bag. ((full shot)) 8k uhd, dslr, soft lighting, high quality, Fujifilm XT3. detailed face and detailed skin. cinematic lighting, movie still"' \
-i 'scheduler="K_EULER"' \
-i 'base_model="SG161222/RealVisXL_V1.0"' \
-i 'num_outputs=1' \
-i 'guidance_scale=7.5' \
-i 'apply_watermark=true' \
-i 'negative_prompt="worst quality, normal quality, low quality, low res, blurry, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting"' \
-i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/alexgenovese/test-endpoint@sha256:7b1b908e2e28ee517404087adadabe32602530d4f44d20cfac8941b9a05ce267curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A realistic fashion photography of an elegant 30 years old blonde woman in an hotel with one red bag. ((full shot)) 8k uhd, dslr, soft lighting, high quality, Fujifilm XT3. detailed face and detailed skin. cinematic lighting, movie still", "scheduler": "K_EULER", "base_model": "SG161222/RealVisXL_V1.0", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "worst quality, normal quality, low quality, low res, blurry, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting", "num_inference_steps": 50 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Add a payment method to run this model.
Each run costs approximately $0.016. Alternatively, try out our featured models for free.
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2023-09-22T19:44:57.083473Z",
"created_at": "2023-09-22T19:44:42.001062Z",
"data_removed": false,
"error": null,
"id": "pnrolmzbk5ldbbj5vssu2e3tky",
"input": {
"width": 1024,
"height": 1024,
"prompt": "A realistic fashion photography of an elegant 30 years old blonde woman in an hotel with one red bag. ((full shot)) 8k uhd, dslr, soft lighting, high quality, Fujifilm XT3. detailed face and detailed skin. cinematic lighting, movie still",
"scheduler": "K_EULER",
"base_model": "SG161222/RealVisXL_V1.0",
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": true,
"negative_prompt": "worst quality, normal quality, low quality, low res, blurry, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting",
"num_inference_steps": 50
},
"logs": "Using seed: 22956\nLoading sdxl pipeline...\nLoading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...: 14%|█▍ | 1/7 [00:00<00:01, 4.77it/s]\nLoading pipeline components...: 43%|████▎ | 3/7 [00:00<00:00, 6.68it/s]\nLoading pipeline components...: 71%|███████▏ | 5/7 [00:00<00:00, 9.09it/s]\nLoading pipeline components...: 86%|████████▌ | 6/7 [00:01<00:00, 4.32it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:02<00:00, 1.50it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:02<00:00, 2.36it/s]\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:07, 6.92it/s]\n 4%|▍ | 2/50 [00:00<00:06, 7.68it/s]\n 6%|▌ | 3/50 [00:00<00:06, 7.44it/s]\n 8%|▊ | 4/50 [00:00<00:06, 7.22it/s]\n 10%|█ | 5/50 [00:00<00:06, 7.13it/s]\n 12%|█▏ | 6/50 [00:00<00:06, 6.95it/s]\n 14%|█▍ | 7/50 [00:00<00:06, 7.14it/s]\n 16%|█▌ | 8/50 [00:01<00:05, 7.48it/s]\n 18%|█▊ | 9/50 [00:01<00:05, 7.58it/s]\n 20%|██ | 10/50 [00:01<00:05, 7.53it/s]\n 22%|██▏ | 11/50 [00:01<00:05, 7.44it/s]\n 24%|██▍ | 12/50 [00:01<00:05, 7.39it/s]\n 26%|██▌ | 13/50 [00:01<00:04, 7.49it/s]\n 28%|██▊ | 14/50 [00:01<00:04, 7.73it/s]\n 30%|███ | 15/50 [00:02<00:04, 7.86it/s]\n 32%|███▏ | 16/50 [00:02<00:04, 8.03it/s]\n 34%|███▍ | 17/50 [00:02<00:04, 8.18it/s]\n 36%|███▌ | 18/50 [00:02<00:03, 8.30it/s]\n 38%|███▊ | 19/50 [00:02<00:03, 8.30it/s]\n 40%|████ | 20/50 [00:02<00:03, 8.34it/s]\n 42%|████▏ | 21/50 [00:02<00:03, 8.42it/s]\n 44%|████▍ | 22/50 [00:02<00:03, 8.47it/s]\n 46%|████▌ | 23/50 [00:02<00:03, 8.26it/s]\n 48%|████▊ | 24/50 [00:03<00:03, 8.31it/s]\n 50%|█████ | 25/50 [00:03<00:02, 8.39it/s]\n 52%|█████▏ | 26/50 [00:03<00:02, 8.45it/s]\n 54%|█████▍ | 27/50 [00:03<00:02, 8.48it/s]\n 56%|█████▌ | 28/50 [00:03<00:02, 8.51it/s]\n 58%|█████▊ | 29/50 [00:03<00:02, 8.53it/s]\n 60%|██████ | 30/50 [00:03<00:02, 8.55it/s]\n 62%|██████▏ | 31/50 [00:03<00:02, 8.56it/s]\n 64%|██████▍ | 32/50 [00:04<00:02, 8.52it/s]\n 66%|██████▌ | 33/50 [00:04<00:01, 8.54it/s]\n 68%|██████▊ | 34/50 [00:04<00:01, 8.56it/s]\n 70%|███████ | 35/50 [00:04<00:01, 8.57it/s]\n 72%|███████▏ | 36/50 [00:04<00:01, 8.58it/s]\n 74%|███████▍ | 37/50 [00:04<00:01, 8.54it/s]\n 76%|███████▌ | 38/50 [00:04<00:01, 8.38it/s]\n 78%|███████▊ | 39/50 [00:04<00:01, 8.27it/s]\n 80%|████████ | 40/50 [00:04<00:01, 8.14it/s]\n 82%|████████▏ | 41/50 [00:05<00:01, 8.27it/s]\n 84%|████████▍ | 42/50 [00:05<00:00, 8.37it/s]\n 86%|████████▌ | 43/50 [00:05<00:00, 8.37it/s]\n 88%|████████▊ | 44/50 [00:05<00:00, 8.43it/s]\n 90%|█████████ | 45/50 [00:05<00:00, 8.48it/s]\n 92%|█████████▏| 46/50 [00:05<00:00, 8.52it/s]\n 94%|█████████▍| 47/50 [00:05<00:00, 8.54it/s]\n 96%|█████████▌| 48/50 [00:05<00:00, 8.56it/s]\n 98%|█████████▊| 49/50 [00:06<00:00, 8.13it/s]\n100%|██████████| 50/50 [00:06<00:00, 8.26it/s]\n100%|██████████| 50/50 [00:06<00:00, 8.12it/s]",
"metrics": {
"predict_time": 15.113188,
"total_time": 15.082411
},
"output": [
"https://replicate.delivery/pbxt/nuOfFs3YzoWbAavGUQ4kB1m50hvGuXplffehCLuKY5djLobGB/out-0.png"
],
"started_at": "2023-09-22T19:44:41.970285Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/pnrolmzbk5ldbbj5vssu2e3tky",
"cancel": "https://api.replicate.com/v1/predictions/pnrolmzbk5ldbbj5vssu2e3tky/cancel"
},
"version": "cacd901fa63f464ab00d47dcca090658defb4d3d75ff047f564151f854d23764"
}Generated in
Using seed: 22956
Loading sdxl pipeline...
Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]
Loading pipeline components...: 14%|█▍ | 1/7 [00:00<00:01, 4.77it/s]
Loading pipeline components...: 43%|████▎ | 3/7 [00:00<00:00, 6.68it/s]
Loading pipeline components...: 71%|███████▏ | 5/7 [00:00<00:00, 9.09it/s]
Loading pipeline components...: 86%|████████▌ | 6/7 [00:01<00:00, 4.32it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:02<00:00, 1.50it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:02<00:00, 2.36it/s]
0%| | 0/50 [00:00<?, ?it/s]
2%|▏ | 1/50 [00:00<00:07, 6.92it/s]
4%|▍ | 2/50 [00:00<00:06, 7.68it/s]
6%|▌ | 3/50 [00:00<00:06, 7.44it/s]
8%|▊ | 4/50 [00:00<00:06, 7.22it/s]
10%|█ | 5/50 [00:00<00:06, 7.13it/s]
12%|█▏ | 6/50 [00:00<00:06, 6.95it/s]
14%|█▍ | 7/50 [00:00<00:06, 7.14it/s]
16%|█▌ | 8/50 [00:01<00:05, 7.48it/s]
18%|█▊ | 9/50 [00:01<00:05, 7.58it/s]
20%|██ | 10/50 [00:01<00:05, 7.53it/s]
22%|██▏ | 11/50 [00:01<00:05, 7.44it/s]
24%|██▍ | 12/50 [00:01<00:05, 7.39it/s]
26%|██▌ | 13/50 [00:01<00:04, 7.49it/s]
28%|██▊ | 14/50 [00:01<00:04, 7.73it/s]
30%|███ | 15/50 [00:02<00:04, 7.86it/s]
32%|███▏ | 16/50 [00:02<00:04, 8.03it/s]
34%|███▍ | 17/50 [00:02<00:04, 8.18it/s]
36%|███▌ | 18/50 [00:02<00:03, 8.30it/s]
38%|███▊ | 19/50 [00:02<00:03, 8.30it/s]
40%|████ | 20/50 [00:02<00:03, 8.34it/s]
42%|████▏ | 21/50 [00:02<00:03, 8.42it/s]
44%|████▍ | 22/50 [00:02<00:03, 8.47it/s]
46%|████▌ | 23/50 [00:02<00:03, 8.26it/s]
48%|████▊ | 24/50 [00:03<00:03, 8.31it/s]
50%|█████ | 25/50 [00:03<00:02, 8.39it/s]
52%|█████▏ | 26/50 [00:03<00:02, 8.45it/s]
54%|█████▍ | 27/50 [00:03<00:02, 8.48it/s]
56%|█████▌ | 28/50 [00:03<00:02, 8.51it/s]
58%|█████▊ | 29/50 [00:03<00:02, 8.53it/s]
60%|██████ | 30/50 [00:03<00:02, 8.55it/s]
62%|██████▏ | 31/50 [00:03<00:02, 8.56it/s]
64%|██████▍ | 32/50 [00:04<00:02, 8.52it/s]
66%|██████▌ | 33/50 [00:04<00:01, 8.54it/s]
68%|██████▊ | 34/50 [00:04<00:01, 8.56it/s]
70%|███████ | 35/50 [00:04<00:01, 8.57it/s]
72%|███████▏ | 36/50 [00:04<00:01, 8.58it/s]
74%|███████▍ | 37/50 [00:04<00:01, 8.54it/s]
76%|███████▌ | 38/50 [00:04<00:01, 8.38it/s]
78%|███████▊ | 39/50 [00:04<00:01, 8.27it/s]
80%|████████ | 40/50 [00:04<00:01, 8.14it/s]
82%|████████▏ | 41/50 [00:05<00:01, 8.27it/s]
84%|████████▍ | 42/50 [00:05<00:00, 8.37it/s]
86%|████████▌ | 43/50 [00:05<00:00, 8.37it/s]
88%|████████▊ | 44/50 [00:05<00:00, 8.43it/s]
90%|█████████ | 45/50 [00:05<00:00, 8.48it/s]
92%|█████████▏| 46/50 [00:05<00:00, 8.52it/s]
94%|█████████▍| 47/50 [00:05<00:00, 8.54it/s]
96%|█████████▌| 48/50 [00:05<00:00, 8.56it/s]
98%|█████████▊| 49/50 [00:06<00:00, 8.13it/s]
100%|██████████| 50/50 [00:06<00:00, 8.26it/s]
100%|██████████| 50/50 [00:06<00:00, 8.12it/s]This output was created using a different version of the model, alexgenovese/test-endpoint:cacd901f.
Examples
Run time and cost
This model costs approximately $0.016 to run on Replicate, or 62 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 12 seconds.
